Aider is worth some tinkering for slightly different reasons than Claude Code.
I find agents do a lot of derpy shit for hard problems but when you've got fairly straightforward things to build it's nice to just spin them up, let them rip and walk away.
Aider feels more like pair programming with an agent, it can kind of be spun up and let rip, but mostly it tries to keep a tighter feedback loop with the user and stay more user directed, which is really powerful when working on challenging things. For stuff like codebase refactors, documentation passes, etc that tight loop feels like overkill though.
Really depends on the type of coding you plan to do and how much.
The amusing thing is people normally recommend using aider to save money. With Aider, you can control the size of the context window, and selectively add/drop files from the window. I typically aim for under 25K tokens at a time. With Gemini, that's about 3 cents per prompt (and often much less when I have only, say, 10 tokens). So for me, I'd need to do well over 3000 coding prompts a month to get to $100. I simply don't use it that much.
Also, at work, I have Copilot, and one can use Aider with that. So I only pay for my personal coding at home.
Getting to the original question - Aider probably lags Claude Code significantly at this point. It's a fantastic tool and I still use it - primarily because it is editor agnostic. But some of the other tools out there do a lot more with agents.
To give you an idea - my combined AI use - including for non-code purposes - is well under $20/mo. Under $10 for most months. I simply don't have that much time to do coding in my free time - even with an AI doing it!
I have tried both, and aider is far less able when it comes to navigating your codebase, and self driving investigation. You are very involved in context management with aider, whereas claude code can use cli commands to do a lot of things itself.
You're in luck, this seems to _only_ support WASM in the browser for the time being.
> Graphite's code architecture is structured to deliver native performance for your graphically intensive workloads on desktop platforms and very low overhead on the web thanks to WebAssembly and WebGPU
Agreed, my company tried buck2 first when evaluating a cargo replacement, but bazel is just so much more mature at this point that it ended up being the natural choice. Thanks for your examples, they helped us get started :)
This is not.. really the right takeaway from his work. That not every true statement within a system is provable from its axioms, or that the consistency of a system is not provable within that system, does not mean that axioms are not useful. Indeed, what math is not grounded in the end by axioms?
This is not some "glossing over some details for a lay audience" situation. It is not a lack of depth. It makes ridiculous claims, fundamentally misrepresenting what this research is, to make it sound cooler and more interesting. This is one of the worst pieces of science journalism I've ever seen.
You typically wouldn't use an array with a million objects in Java if you cared about performance though (for exactly that reason), you'd architect it some other way. Using SoA style when appropriate, for example.
